Santiago Profile picture
Oct 2, 2020 19 tweets 3 min read Read on X
You might have finished the engine, but there's still a lot of work to put the entire car together.

A Machine Learning model is just a small piece of the equation.

A lot more needs to happen. Let's talk about that.

🧵👇
For simplicity's sake, let's imagine a model that takes a picture of an animal and classifies it among 100 different species.

▫️Input: pre-processed pixels of the image.
▫️Output: a score for each one of the 100 species.

Final answer is the species with the highest score.

👇
There's a lot of work involved in creating a model like this. There's even more work involved in preparing the data to train it.

But it doesn't stop there.

The model is just the start, the core, the engine of what will become a fully-fledged car.

👇
Unfortunately, many companies are hyper-focused on creating these models and forget that productizing them is not just a checkbox in the process.

Reports are pointing out that ~90% of Data Science projects never make it to production!

I'm not surprised.

👇
Our model predicting species is now ready!

— "Good job, everyone!"

— "Oh, wait. Now what? How do we use this thing?"

Let's take our model into production step by step.

👇
First, we need to wrap the model with code that:

1. Pre-processes the input image
2. Translates the output into an appropriate answer

I call this the "extended model." Complexity varies depending on your needs.

👇
Frequently, processing a single image at a time is not enough, and you need to process batches of pictures (you know, to speed things up a bit.)

Doing this requires a non-trivial amount of work.

👇
Now we need to expose the functionality of the extended model.

Usually, you can do this by creating a wrapper API (REST or RPC) and have client applications use it to communicate with the model.

Loading the model in memory brings some other exciting challenges.

👇
Of course, we can't trust what comes into that API, so we need to validate its input:

▫️What's the format of the image we are getting?
▫️What happens if it doesn't exist?
▫️Does it have the expected resolution?
▫️Is it base64? URL?
▫️...

👇
Now that our API is ready, we need to host it. Maybe with a cloud provider. Several things to worry about here:

▫️Package API and model in a container
▫️Where do we deploy it?
▫️How do we deploy it?
▫️How do we take advantage of acceleration?

👇
Also:

▫️How long do we have to return an answer?
▫️How many requests per second can we handle?
▫️Do we need automatic scaling?
▫️What are the criteria to scale in and out?
▫️How can we tell when a model is down?
▫️How do we log what happens?

👇
Let's say we made it.

At this point, we have a frozen, stuck-in-time version of our model deployed.

But we aren't done yet. Far from it!

By now, there's probably a newer version of the model ready to go.

How do we deploy that version? Do we need to start again?

👇
And of course, it would be ideal if you don't just snap the new version of the model in and pray that quality doesn't go down, right?

You want old and new side by side. Then migrate traffic over gradually.

This requires more work.

👇
Creating the pipeline that handles taking new models and hosting them in production takes a lot of planning and effort.

And you are probably thinking, "That's MLOps!"

Yes, it is! But giving it a name doesn't make it less complicated.

👇
And there's more.

As we collect more and more data, we need to train new versions of our model.

We can't expect our people to do this manually. We need to automate the training pipeline.

A whole lot more work!

👇
Some questions:

1. Where's the data coming from?
2. How should it be split?
3. How much data should be used to retrain?
4. How will the training scripts run?
5. What metrics do we need?
6. How to evaluate the quality of the model?

These aren't simply "Yes" or "No" answers.

👇
At this point, are we done yet?

Well, not quite 😞

We need to worry about monitoring our model. How is it performing?

That pesky "concept drift" ensures that the quality of our results will rapidly decay. We need to be on top of it!

👇
And there's even more.

Here are some must-haves for well-rounded, safe production systems that I haven't covered yet:

▫️Ethics
▫️Data capturing and storage
▫️Data quality
▫️Integrating human feedback

👇
Here is the bottom line:

Creating a model with predictive capacity is just a small part of a much bigger equation.

There aren't a lot of companies that understand the entire picture. This opens up a lot of opportunities.

Opportunities for you and me.

• • •

Missing some Tweet in this thread? You can try to force a refresh
 

Keep Current with Santiago

Santiago Profile picture

Stay in touch and get notified when new unrolls are available from this author!

Read all threads

This Thread may be Removed Anytime!

PDF

Twitter may remove this content at anytime! Save it as PDF for later use!

Try unrolling a thread yourself!

how to unroll video
  1. Follow @ThreadReaderApp to mention us!

  2. From a Twitter thread mention us with a keyword "unroll"
@threadreaderapp unroll

Practice here first or read more on our help page!

More from @svpino

Apr 30
Improve your LLM-based applications by 200%:

Build an LLM-as-a-Judge evaluator and integrate it with your system.

This sounds harder than it is.

Here is how to do it and the things you need to keep in mind:

1/11 Image
(LLM-as-a-judge is one of the topics I teach in my cohort. The next iteration starts next week. You can join at .)

LLM-as-a-Judge is a technique that uses an LLM to evaluate the quality of the outputs from your application.

2/11ml.school
There are three specific scenarios you can test with a judge:

1. Choose the best of 2 answers (pairwise comparison)

2. Assess specific qualities of an answer (reference-free)

3. Evaluate the answer based on additional context (reference-based)

3/11 Image
Read 11 tweets
Apr 18
Falling off ladders to claim insurance checks is a multi-million-dollar fraud business in the US.

People bury insurance companies in paperwork to steal from them.

Enter RAG.

Here is how RAG is becoming the cheaters' worst nightmare (and how you can do the same):

1/8 Image
An insurance claim can easily have 20,000 pages, and somebody must read them all!

I work with @EyeLevel, and we built a fraud detection system using their GroundX platform.

Best RAG use case I've seen—and you can use GroundX to build your own in any vertical.

2/8
Here is how you stop the cheaters:

First, the application ingests all of the documentation. All 20,000+ pages go into the database.

GroundX uses a pretrained vision model to ingest and understand documents, which is especially good for complex documents.

3/8
Read 8 tweets
Mar 7
Here is an explanation of what MCP is, how it works, and why I think it's awesome.

I will also show you the MCP server I'm building.

This is good stuff.
For those who like YouTube better:



By the way, I won't like you anymore if you don't subscribe to my channel.
Here is where I'd start reading to understand what MCP is and what it does:



After you read "Core architecture", jump around all the other concepts. They will give you an idea of everything you can do with MCP. modelcontextprotocol.io/docs/concepts/…Image
Read 4 tweets
Jan 16
AWS is irrefutable proof that the right software with a great backend can succeed despite horrible UI/UX.
Craigslist: “hold my beer”
eBay: “Did anyone said ‘horrible UI’?”
Read 11 tweets
Nov 12, 2024
This is worth 1,000+ hours of engineering work every year:

1. Reproducing a bug
2. Getting detailed debug data
3. Writing how to reproduce it
4. Putting it all together in a good bug report

This tool can do all of this and cut the time it takes to fix the bug by 70%+:
makes the reporting and fixing process really fast!

Click once, and engineers get:

• Console logs
• Network requests
• Timing waterfall
• Repro steps
• Session & user details
• Device & OS
• Backend logs

Check the attached video. Jam.dev
It's just a browser extension - so anyone can report bugs w/ technical details.

Even after the bug just happened!

You can click instant replay, and Jam will create a detailed report with real-time data and video up to the last 2 minutes.
Read 4 tweets
Oct 1, 2024
My new soon-to-be Linux laptop right before I start assembling it. Image
RAM and SSD are now installed. Took me 1 minute and I didn’t even read the manual. Image
The packaging is very nice. A lot of cardboard. This thing comes well protected.

Mostly, frustration-free packaging. Reminiscent of Apple’s boxes. Image
Read 13 tweets

Did Thread Reader help you today?

Support us! We are indie developers!


This site is made by just two indie developers on a laptop doing marketing, support and development! Read more about the story.

Become a Premium Member ($3/month or $30/year) and get exclusive features!

Become Premium

Don't want to be a Premium member but still want to support us?

Make a small donation by buying us coffee ($5) or help with server cost ($10)

Donate via Paypal

Or Donate anonymously using crypto!

Ethereum

0xfe58350B80634f60Fa6Dc149a72b4DFbc17D341E copy

Bitcoin

3ATGMxNzCUFzxpMCHL5sWSt4DVtS8UqXpi copy

Thank you for your support!

Follow Us!

:(